{"id":"https://openalex.org/W4387892091","doi":"https://doi.org/10.48550/arxiv.2310.13424","title":"FLTracer: Accurate Poisoning Attack Provenance in Federated Learning","display_name":"FLTracer: Accurate Poisoning Attack Provenance in Federated Learning","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4387892091","doi":"https://doi.org/10.48550/arxiv.2310.13424"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.13424","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.13424","pdf_url":"https://arxiv.org/pdf/2310.13424","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.13424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100390745","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0009-0009-3931-7404"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Xinyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669230","display_name":"Qingyu Liu","orcid":"https://orcid.org/0009-0000-9774-808X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qingyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072485378","display_name":"Zhongjie Ba","orcid":"https://orcid.org/0000-0003-0921-8869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ba, Zhongjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104081006","display_name":"Yuan Hong","orcid":"https://orcid.org/0009-0007-2269-0945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091687257","display_name":"Tianhang Zheng","orcid":"https://orcid.org/0000-0002-5151-1527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Tianhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078406349","display_name":"Feng Lin","orcid":"https://orcid.org/0000-0001-5240-5200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Feng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5105297718","display_name":"Kui Ren","orcid":"https://orcid.org/0000-0002-1969-2591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Kui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100390745"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8464457988739014},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.7561438083648682},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5433791875839233},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"False positive rate","score":0.5135043263435364},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.4561244249343872},{"id":"https://openalex.org/keywords/attack-model","display_name":"Attack model","score":0.4405694007873535},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42199233174324036},{"id":"https://openalex.org/keywords/true-positive-rate","display_name":"True positive rate","score":0.4204385578632355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39498627185821533},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37372785806655884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3151181936264038},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2966648042201996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464457988739014},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7561438083648682},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5433791875839233},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.5135043263435364},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.4561244249343872},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.4405694007873535},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42199233174324036},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.4204385578632355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39498627185821533},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37372785806655884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3151181936264038},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2966648042201996},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.13424","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.13424","pdf_url":"https://arxiv.org/pdf/2310.13424","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2310.13424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.13424","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.13424","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.13424","pdf_url":"https://arxiv.org/pdf/2310.13424","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387892091.pdf","grobid_xml":"https://content.openalex.org/works/W4387892091.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2027184711","https://openalex.org/W3119537175","https://openalex.org/W101962219","https://openalex.org/W2951146195","https://openalex.org/W4292605373","https://openalex.org/W2735767444","https://openalex.org/W3123215897","https://openalex.org/W2810356275","https://openalex.org/W2208028087","https://openalex.org/W3164550676"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"is":[3,26,170,228],"a":[4,16,51,143],"promising":[5],"distributed":[6,97],"learning":[7],"approach":[8],"that":[9,24,64,134,201],"enables":[10],"multiple":[11],"clients":[12],"to":[13,28,87,113,148,166],"collaboratively":[14],"train":[15],"shared":[17],"global":[18,38],"model.":[19],"However,":[20],"recent":[21],"studies":[22],"show":[23,63,200],"FL":[25,56,109],"vulnerable":[27],"various":[29,116],"poisoning":[30],"attacks,":[31],"which":[32,85],"can":[33],"degrade":[34],"the":[35,107,120,153,159,179,195],"performance":[36,89],"of":[37,128,181,209,218],"models":[39],"or":[40],"introduce":[41],"backdoors":[42],"into":[43],"them.":[44],"In":[45],"this":[46,162],"paper,":[47],"we":[48,104,141,185],"first":[49,108],"conduct":[50],"comprehensive":[52],"study":[53],"on":[54,137],"prior":[55],"attacks":[57,117],"and":[58,74,95,118,125,157,169,190],"detection":[59,67,78,147,183,225],"methods.":[60,226],"The":[61],"results":[62],"all":[65],"existing":[66,132],"methods":[68,79],"are":[69],"only":[70],"effective":[71,171],"against":[72],"limited":[73],"specific":[75],"attacks.":[76],"Most":[77],"suffer":[80],"from":[81,131],"high":[82],"false":[83,215],"positives,":[84],"lead":[86],"significant":[88],"degradation,":[90],"especially":[91],"in":[92,173],"not":[93],"independent":[94],"identically":[96],"(non-IID)":[98],"settings.":[99,175],"To":[100,176],"address":[101],"these":[102],"issues,":[103],"propose":[105,142],"FLTracer,":[106],"attack":[110,121],"provenance":[111],"framework":[112],"accurately":[114],"detect":[115],"trace":[119],"time,":[122],"objective,":[123],"type,":[124],"poisoned":[126],"location":[127],"updates.":[129],"Different":[130],"methodologies":[133],"rely":[135],"solely":[136],"cross-client":[138],"anomaly":[139],"detection,":[140],"Kalman":[144],"filter-based":[145],"cross-round":[146],"identify":[149],"adversaries":[150],"by":[151],"seeking":[152],"behavior":[154],"changes":[155],"before":[156],"after":[158],"attack.":[160],"Thus,":[161],"makes":[163],"it":[164],"resilient":[165],"data":[167],"heterogeneity":[168],"even":[172],"non-IID":[174],"further":[177],"improve":[178],"accuracy":[180],"our":[182],"method,":[184],"employ":[186],"four":[187],"novel":[188],"features":[189],"capture":[191],"their":[192],"anomalies":[193],"with":[194],"joint":[196],"decisions.":[197],"Extensive":[198],"evaluations":[199],"FLTracer":[202],"achieves":[203],"an":[204,213],"average":[205,214],"true":[206],"positive":[207,216],"rate":[208,217],"over":[210],"$96.88\\%$":[211],"at":[212,230],"less":[219],"than":[220],"$2.67\\%$,":[221],"significantly":[222],"outperforming":[223],"SOTA":[224],"\\footnote{Code":[227],"available":[229],"\\url{https://github.com/Eyr3/FLTracer}.}":[231]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}